{"id":"0935c688-2a34-4b1b-ace4-57e8b06deebd","slug":"clawhub-jingzhao-l-iterate-skill","name":"Iterate","description":"Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory SHA256 checksum verification. v3.0 adds a dual-mode (the original iterate mode plus a defensive-programming mode via /iterate defensive) that performs normal incremental coding tasks with defensive discipline end-to-end.","canonicalUrl":"https://www.xpersona.co/agent/clawhub-jingzhao-l-iterate-skill","sourceUrl":"https://clawhub.ai/jingzhao-l/iterate-skill","homepage":"https://clawhub.ai/jingzhao-l/skills/iterate-skill","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/jingzhao-l/skills/iterate-skill"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"3.4.4","freshnessAt":"2026-10-09T13:00:16.525Z","freshnessLabel":"Oct 9, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Oct 9, 2026"},{"label":"Vendor","value":"Clawhub"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"3.4.4"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Clawhub","href":"https://clawhub.ai/jingzhao-l/skills/iterate-skill","sourceUrl":"https://clawhub.ai/jingzhao-l/skills/iterate-skill","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T13:00:16.526Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-jingzhao-l-iterate-skill/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jingzhao-l-iterate-skill/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-09T13:00:16.526Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"2.6K downloads","href":"https://clawhub.ai/jingzhao-l/iterate-skill","sourceUrl":"https://clawhub.ai/jingzhao-l/iterate-skill","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T13:00:16.526Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"3.4.4","href":"https://clawhub.ai/jingzhao-l/iterate-skill","sourceUrl":"https://clawhub.ai/jingzhao-l/iterate-skill","sourceType":"release","confidence":"medium","observedAt":"2026-10-04T02:10:58.627Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-jingzhao-l-iterate-skill/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jingzhao-l-iterate-skill/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["2.6K downloads","Trust evidence available"],"agentCard":{"name":"Iterate","description":"Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory SHA256 checksum verification. v3.0 adds a dual-mode (the original iterate mode plus a defensive-programming mode via /iterate defensive) that performs normal incremental coding tasks with defensive discipline end-to-end.","source":"CLAWHUB","sourceId":"clawhub:s1722v1f08paw6feta6f0f11t18awbn2:iterate-skill","homepage":"https://clawhub.ai/jingzhao-l/skills/iterate-skill","repository":"https://clawhub.ai/jingzhao-l/iterate-skill","documentation":"https://www.xpersona.co/agent/clawhub-jingzhao-l-iterate-skill","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"text","snippet":"Step 0 — Onboarding Check\n  └─ Locate project root → check ITERATE.md → drift detection → (onboard if needed)\n\nSetup\n  └─ Extract goal → load config → read project context (ITERATE.md → CLAUDE.md → …) → create isolated branch/worktree\n\nLoop (round = 1 .. max_rounds)\n  ├─ Phase 0: Dimension Planning (route goal → dimension_sets | ad-hoc redefine, bounded record)\n  ├─ Phase 1: N-dimension parallel review (N = enabled dimensions count, default 9)\n  ├─ Phase 2: Atomic fixes (direct)\n  ├─ Phase 3: Architectural fixes (approval → serial sub-agents)\n  ├─ Phase 4: Record round results\n  └─ Phase 5: Validate → merge → push\n\nSummary"},{"kind":"example","language":"bash","snippet":"iterate onboard      # 交互式向导（多路引导：首次/非首次自动分支）\niterate personalize  # 个性化配置（项目中途追加约束，9 步向导）\niterate personalize --clear [--yes]  # 清空所有个性化配置（结构化规则 + ITERATE.md 相关段落）\niterate show         # 只读查看合并后的配置与个性化详情（支持 --json）\niterate refresh      # 增量刷新（保留用户手写区；支持 --json / --dry-run --json 结构化报告）\niterate reonboard    # 完整重新 onboarding（备份旧文件）\niterate doctor       # 项目健康诊断（onboarding/config/维度/漂移等全项检查；--strict 将 warning 一并判失败；--fix 安全修复；--json / --json-out 结构化输出）\niterate status       # 查看 onboarding 状态和漂移检测（--json 含 onboarded、config_exists/config_ok、drift_detected 与明细列表）\niterate guard pre-check [targets...]   # 编辑前静态校验（目标存在/工作区干净/manifest 就绪；只读，从不执行命令；--json）\niterate guard post-check [targets...]  # 编辑后执行 validation.commands 并核对结果（--dry-run 只预览命令不执行；--json）\niterate invariant      # 项目级不变量校验（--dry-run 预览；--json）\niterate fingerprint verify  # 校验 manifest 指纹漂移（--json）\niterate config       # 非交互式查看全部可设配置值（支持 --json）\niterate config get <key>   # 读取单个配置项的解析值（支持 --json，输出 {\"key\": value}）\niterate config set <key> <value>  # 校验并写回单个配置项（自动备份；--json 输出确认对象）\niterate update       # 自更新：SHA-256 校验后刷新助手技能目录 + 重装 CLI（--check 只对比版本；--yes 跳过确认；--assistants 限定刷新范围，未知助手名报错而非静默跳过）"}]}}